Ruojin Cai

About

Ruojin Cai is a Ph.D. candidate in Computer Science at Cornell University, advised by Professors Bharath Hariharan and Noah Snavely, and graduating in Summer 2025. Her research focuses on 3D computer vision and spatial intelligence, particularly how models reconstruct and interpret the 3D world under challenging conditions. She holds a bachelor’s degree from Tsinghua University, has interned at Adobe and Google, and received the 2022 Snap Research Fellowship.

Research Focus

Ruojin’s research focuses on 3D computer vision, with the goal of building models that can perceive and reason about the 3D world, advancing spatial intelligence in machines. She studies core challenges in 3D reconstruction under sparse-view or ambiguous settings, where traditional geometric methods often fail. Her key insight is to address these challenges by leveraging learned priors from generative video models and geometric vision models to improve robustness under limited or ambiguous observations. Building on this, she aims to advance 3D foundation models and integrate reasoning into vision tasks, with potential applications in robotics and embodied AI. Her long-term goal is to develop truly spatially intelligent systems that can not only perceive but also reason about and act within complex, real-world environments.